{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:46:42Z","timestamp":1774021602780,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":83,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730656","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:40:47Z","timestamp":1753260047000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5465-4390","authenticated-orcid":false,"given":"Lucas N.","family":"Alegre","sequence":"first","affiliation":[{"name":"Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil and Disney Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4439-0023","authenticated-orcid":false,"given":"Agon","family":"Serifi","sequence":"additional","affiliation":[{"name":"Disney Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8971-6843","authenticated-orcid":false,"given":"Ruben","family":"Grandia","sequence":"additional","affiliation":[{"name":"Disney Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6591-8803","authenticated-orcid":false,"given":"David","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Disney Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7440-5655","authenticated-orcid":false,"given":"Espen","family":"Knoop","sequence":"additional","affiliation":[{"name":"Disney Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1952-1266","authenticated-orcid":false,"given":"Moritz","family":"B\u00e4cher","sequence":"additional","affiliation":[{"name":"Disney Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_3_2_1","doi-asserted-by":"crossref","unstructured":"Mazen Al\u00a0Borno Martin de Lasa and Aaron Hertzmann. 2013. Trajectory Optimization for Full-Body Movements with Complex Contacts. IEEE Transactions on Visualization and Computer Graphics 19 8 (2013) 1405\u20131414. doi:10.1109\/TVCG.2012.325","DOI":"10.1109\/TVCG.2012.325"},{"key":"e_1_3_3_3_3_1","series-title":"Proceedings of Machine Learning Research","first-page":"394","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Alegre Lucas\u00a0N.","year":"2022","unstructured":"Lucas\u00a0N. Alegre, Ana L.\u00a0C. Bazzan, and Bruno\u00a0C. da Silva. 2022. Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162), Kamalika Chaudhuri, Stefanie Jegelka, Le\u00a0Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 394\u2013413."},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3545946.3598872"},{"key":"e_1_3_3_3_5_1","volume-title":"Proceedings of the Ninth International Conference on Learning Representations","author":"Andrychowicz Marcin","year":"2021","unstructured":"Marcin Andrychowicz, Anton Raichuk, Piotr Sta\u0144czyk, Manu Orsini, Sertan Girgin, Rapha\u00ebl Marinier, Leonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, Sylvain Gelly, and Olivier Bachem. 2021. What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study. In Proceedings of the Ninth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nIAxjsniDzg"},{"key":"e_1_3_3_3_6_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Barreto Andr\u00e9","year":"2019","unstructured":"Andr\u00e9 Barreto, Diana Borsa, Shaobo Hou, Gheorghe Comanici, Eser Ayg\u00fcn, Philippe Hamel, Daniel Toyama, Jonathan Hunt, Shibl Mourad, David Silver, and Doina Precup. 2019. The option keyboard combining skills in reinforcement learning. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 1169, 11\u00a0pages."},{"key":"e_1_3_3_3_7_1","unstructured":"Andr\u00e9 Barreto Will Dabney R\u00e9mi Munos Jonathan\u00a0J Hunt Tom Schaul Hado\u00a0P van Hasselt and David Silver. 2017. Successor features for transfer in reinforcement learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"crossref","unstructured":"Kevin Bergamin Simon Clavet Daniel Holden and James\u00a0Richard Forbes. 2019. DReCon: data-driven responsive control of physics-based characters. ACM Trans. Graph. 38 6 Article 206 (Nov. 2019) 11\u00a0pages. doi:10.1145\/3355089.3356536","DOI":"10.1145\/3355089.3356536"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"crossref","unstructured":"Xuxin Cheng Yandong Ji Junming Chen Ruihan Yang Ge Yang and Xiaolong Wang. 2024. Expressive whole-body control for humanoid robots. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.16796 (2024).","DOI":"10.15607\/RSS.2024.XX.107"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274247.3274506"},{"key":"e_1_3_3_3_11_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings","author":"Clevert Djork-Arn\u00e9","year":"2016","unstructured":"Djork-Arn\u00e9 Clevert, Thomas Unterthiner, and Sepp Hochreiter. 2016. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1511.07289"},{"key":"e_1_3_3_3_12_1","volume-title":"CMU Graphics Lab Motion Capture Database","year":"2001","unstructured":"CMU. 2001. CMU Graphics Lab Motion Capture Database. http:\/\/mocap.cs.cmu.edu\/"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"crossref","unstructured":"Stelian Coros Philippe Beaudoin and Michiel van\u00a0de Panne. 2010. Generalized biped walking control. ACM Trans. Graph. 29 4 Article 130 (July 2010) 9\u00a0pages. doi:10.1145\/1778765.1781156","DOI":"10.1145\/1778765.1781156"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Peter Dayan. 1993. Improving Generalization for Temporal Difference Learning: The Successor Representation. Neural Computation 5 4 (1993) 613\u2013624. doi:10.1162\/neco.1993.5.4.613","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618205"},{"key":"e_1_3_3_3_16_1","volume-title":"Advances in Neural Information Processing Systems","author":"Felten Florian","year":"2023","unstructured":"Florian Felten, Lucas\u00a0N. Alegre, Ann Now\u00e9, Ana L.\u00a0C. Bazzan, El-Ghazali Talbi, Gr\u00e9goire Danoy, and Bruno\u00a0C. da Silva. 2023. A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning. In Advances in Neural Information Processing Systems (New Orleans, USA), Vol.\u00a036."},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"crossref","unstructured":"Florian Felten El-Ghazali Talbi and Gr\u00e9goire Danoy. 2024. Multi-Objective Reinforcement Learning based on Decomposition: A taxonomy and framework. Journal of Artificial Intelligence Research 79 (2024) 679\u2013723.","DOI":"10.1613\/jair.1.15702"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"crossref","unstructured":"Levi Fussell Kevin Bergamin and Daniel Holden. 2021. SuperTrack: motion tracking for physically simulated characters using supervised learning. ACM Trans. Graph. 40 6 Article 197 (Dec. 2021) 13\u00a0pages. doi:10.1145\/3478513.3480527","DOI":"10.1145\/3478513.3480527"},{"key":"e_1_3_3_3_19_1","unstructured":"Jonas Gehring Deepak Gopinath Jungdam Won Andreas Krause Gabriel Synnaeve and Nicolas Usunier. 2023. Leveraging Demonstrations with Latent Space Priors. Transactions on Machine Learning Research (2023). https:\/\/openreview.net\/forum?id=OzGIu4T4Cz"},{"key":"e_1_3_3_3_20_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.103"},{"key":"e_1_3_3_3_22_1","unstructured":"Zhaoyuan Gu Junheng Li Wenlan Shen Wenhao Yu Zhaoming Xie Stephen McCrory Xianyi Cheng Abdulaziz Shamsah Robert Griffin C\u00a0Karen Liu et\u00a0al. 2025. Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control Planning and Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.02116 (2025)."},{"key":"e_1_3_3_3_23_1","unstructured":"Sehoon Ha Joonho Lee Michiel van\u00a0de Panne Zhaoming Xie Wenhao Yu and Majid Khadiv. 2024. Learning-based legged locomotion; state of the art and future perspectives. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.01152 (2024)."},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"crossref","unstructured":"Perttu H\u00e4m\u00e4l\u00e4inen Joose Rajam\u00e4ki and C.\u00a0Karen Liu. 2015. Online control of simulated humanoids using particle belief propagation. ACM Trans. Graph. 34 4 Article 81 (July 2015) 13\u00a0pages. doi:10.1145\/2767002","DOI":"10.1145\/2767002"},{"key":"e_1_3_3_3_25_1","series-title":"Proceedings of Machine Learning Research","first-page":"4105","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Hasenclever Leonard","year":"2020","unstructured":"Leonard Hasenclever, Fabio Pardo, Raia Hadsell, Nicolas Heess, and Josh Merel. 2020. CoMic: Complementary Task Learning & Mimicry for Reusable Skills. In Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0119), Hal\u00a0Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 4105\u20134115. https:\/\/proceedings.mlr.press\/v119\/hasenclever20a.html"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"crossref","unstructured":"Conor\u00a0F. Hayes Roxana R\u0103dulescu Eugenio Bargiacchi Johan K\u00e4llstr\u00f6m Matthew Macfarlane Mathieu Reymond Timothy Verstraeten Luisa\u00a0M. Zintgraf Richard Dazeley Fredrik Heintz Enda Howley Athirai\u00a0A. Irissappane Patrick Mannion Ann Now\u00e9 Gabriel Ramos Marcello Restelli Peter Vamplew and Diederik\u00a0M. Roijers. 2022. A practical guide to multi-objective reinforcement learning and planning. Autonomous Agents and Multi-Agent Systems 36 1 (13 Apr 2022) 26. doi:10.1007\/s10458-022-09552-y","DOI":"10.1007\/s10458-022-09552-y"},{"key":"e_1_3_3_3_27_1","unstructured":"Tairan He Wenli Xiao Toru Lin Zhengyi Luo Zhenjia Xu Zhenyu Jiang Changliu Liu Guanya Shi Xiaolong Wang Linxi Fan and Yuke Zhu. 2024. HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.21229 (2024)."},{"key":"e_1_3_3_3_28_1","unstructured":"Nicolas Heess Dhruva Tb Srinivasan Sriram Jay Lemmon Josh Merel Greg Wayne Yuval Tassa Tom Erez Ziyu Wang SM Eslami et\u00a0al. 2017. Emergence of locomotion behaviours in rich environments. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.02286 (2017)."},{"key":"e_1_3_3_3_29_1","volume-title":"Advances in Neural Information Processing Systems","author":"Heess Nicolas","year":"2015","unstructured":"Nicolas Heess, Gregory Wayne, David Silver, Timothy Lillicrap, Tom Erez, and Yuval Tassa. 2015. Learning Continuous Control Policies by Stochastic Value Gradients. In Advances in Neural Information Processing Systems , C.\u00a0Cortes, N.\u00a0Lawrence, D.\u00a0Lee, M.\u00a0Sugiyama, and R.\u00a0Garnett (Eds.), Vol.\u00a028. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2015\/file\/148510031349642de5ca0c544f31b2ef-Paper.pdf"},{"key":"e_1_3_3_3_30_1","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218414"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"crossref","unstructured":"Julian Ibarz Jie Tan Chelsea Finn Mrinal Kalakrishnan Peter Pastor and Sergey Levine. 2021. How to train your robot with deep reinforcement learning: lessons we have learned. The International Journal of Robotics Research 40 4-5 (2021) 698\u2013721. doi:10.1177\/0278364920987859","DOI":"10.1177\/0278364920987859"},{"key":"e_1_3_3_3_33_1","unstructured":"Dohyeong Kim Hyeokjin Kwon Junseok Kim Gunmin Lee and Songhwai Oh. 2024. Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach. arxiv:https:\/\/arXiv.org\/abs\/2409.15755\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/2409.15755"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1781155"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"crossref","unstructured":"Libin Liu KangKang Yin and Baining Guo. 2015. Improving Sampling-based Motion Control. Computer Graphics Forum 34 2 (2015) 415\u2013423. doi:10.1111\/cgf.12571 arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.12571","DOI":"10.1111\/cgf.12571"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"crossref","unstructured":"Libin Liu KangKang Yin Michiel van\u00a0de Panne and Baining Guo. 2012. Terrain runner: control parameterization composition and planning for highly dynamic motions. ACM Transactions on Graphics (TOG) 31 6 (2012) 154.","DOI":"10.1145\/2366145.2366173"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"crossref","unstructured":"Libin Liu KangKang Yin Michiel van\u00a0de Panne Tianjia Shao and Weiwei Xu. 2010. Sampling-based contact-rich motion control. ACM Trans. Graph. 29 4 Article 128 (July 2010) 10\u00a0pages. doi:10.1145\/1778765.1778865","DOI":"10.1145\/1778765.1778865"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"e_1_3_3_3_39_1","volume-title":"Proceedings of The Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Makoviychuk Viktor","year":"2021","unstructured":"Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo, Michelle Lu, Kier Storey, Miles Macklin, David Hoeller, Nikita Rudin, Arthur Allshire, Ankur Handa, and Gavriel State. 2021. Isaac Gym: High Performance GPU Based Physics Simulation For Robot Learning. In Proceedings of The Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=fgFBtYgJQX_"},{"key":"e_1_3_3_3_40_1","volume-title":"International Conference on Learning Representations","author":"Merel Josh","year":"2019","unstructured":"Josh Merel, Leonard Hasenclever, Alexandre Galashov, Arun Ahuja, Vu Pham, Greg Wayne, Yee\u00a0Whye Teh, and Nicolas Heess. 2019. Neural Probabilistic Motor Primitives for Humanoid Control. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJl6TjRcY7"},{"key":"e_1_3_3_3_41_1","unstructured":"Josh Merel Yuval Tassa Dhruva TB Sriram Srinivasan Jay Lemmon Ziyu Wang Greg Wayne and Nicolas Heess. 2017. Learning human behaviors from motion capture by adversarial imitation. arxiv:https:\/\/arXiv.org\/abs\/1707.02201\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/1707.02201"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"crossref","unstructured":"Josh Merel Saran Tunyasuvunakool Arun Ahuja Yuval Tassa Leonard Hasenclever Vu Pham Tom Erez Greg Wayne and Nicolas Heess. 2020. Catch & Carry: reusable neural controllers for vision-guided whole-body tasks. ACM Trans. Graph. 39 4 Article 39 (Aug. 2020) 14\u00a0pages. doi:10.1145\/3386569.3392474","DOI":"10.1145\/3386569.3392474"},{"key":"e_1_3_3_3_43_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Mescheder Lars","year":"2018","unstructured":"Lars Mescheder, Sebastian Nowozin, and Andreas Geiger. 2018. Which Training Methods for GANs do actually Converge?. In Proceedings of the 35th International Conference on Machine Learning."},{"key":"e_1_3_3_3_44_1","series-title":"Proceedings of Machine Learning Research","first-page":"1928","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","volume":"48","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria\u00a0Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. In Proceedings of The 33rd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a048), Maria\u00a0Florina Balcan and Kilian\u00a0Q. Weinberger (Eds.). PMLR, New York, New York, USA, 1928\u20131937. https:\/\/proceedings.mlr.press\/v48\/mniha16.html"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei\u00a0A Rusu Joel Veness Marc\u00a0G Bellemare Alex Graves Martin Riedmiller Andreas\u00a0K Fidjeland Georg Ostrovski et\u00a0al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529\u2013533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778808"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"crossref","unstructured":"Igor Mordatch Emanuel Todorov and Zoran Popovi\u0107. 2012. Discovery of complex behaviors through contact-invariant optimization. ACM Trans. Graph. 31 4 Article 43 (July 2012) 8\u00a0pages. doi:10.1145\/2185520.2185539","DOI":"10.1145\/2185520.2335394"},{"key":"e_1_3_3_3_48_1","series-title":"(NIPS\u201916)","first-page":"271","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Nowozin Sebastian","year":"2016","unstructured":"Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. 2016. f-GAN: training generative neural samplers using variational divergence minimization. In Proceedings of the 30th International Conference on Neural Information Processing Systems (Barcelona, Spain) (NIPS\u201916). Curran Associates Inc., Red Hook, NY, USA, 271\u2013279."},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"crossref","unstructured":"Soohwan Park Hoseok Ryu Seyoung Lee Sunmin Lee and Jehee Lee. 2019. Learning predict-and-simulate policies from unorganized human motion data. ACM Trans. Graph. 38 6 Article 205 (Nov. 2019) 11\u00a0pages. doi:10.1145\/3355089.3356501","DOI":"10.1145\/3355089.3356501"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Pieter Abbeel Sergey Levine and Michiel van\u00a0de Panne. 2018a. DeepMimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graph. 37 4 Article 143 (July 2018) 14\u00a0pages. doi:10.1145\/3197517.3201311","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Glen Berseth Kangkang Yin and Michiel Van De\u00a0Panne. 2017. DeepLoco: dynamic locomotion skills using hierarchical deep reinforcement learning. ACM Trans. Graph. 36 4 Article 41 (July 2017) 13\u00a0pages. doi:10.1145\/3072959.3073602","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_3_3_52_1","volume-title":"MCP: learning composable hierarchical control with multiplicative compositional policies","author":"Peng Xue\u00a0Bin","year":"2019","unstructured":"Xue\u00a0Bin Peng, Michael Chang, Grace Zhang, Pieter Abbeel, and Sergey Levine. 2019. MCP: learning composable hierarchical control with multiplicative compositional policies. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Angjoo Kanazawa Jitendra Malik Pieter Abbeel and Sergey Levine. 2018b. SFV: reinforcement learning of physical skills from videos. ACM Trans. Graph. 37 6 Article 178 (Dec. 2018) 14\u00a0pages. doi:10.1145\/3272127.3275014","DOI":"10.1145\/3272127.3275014"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Ze Ma Pieter Abbeel Sergey Levine and Angjoo Kanazawa. 2021. AMP: adversarial motion priors for stylized physics-based character control. ACM Trans. Graph. 40 4 Article 144 (jul 2021) 20\u00a0pages. doi:10.1145\/3450626.3459670","DOI":"10.1145\/3450626.3459670"},{"key":"e_1_3_3_3_55_1","volume-title":"3D Animation and 2D Cartoons Made Simple.","year":"2023","unstructured":"Reallusion. 2023. 3D Animation and 2D Cartoons Made Simple.https:\/\/www.reallusion.com https:\/\/actorcore.reallusion.com\/motion\/pack\/studio-mocap-sword-and-shield-stunts, https:\/\/actorcore.reallusion.com\/motion\/pack\/studio-mocap-sword-and-shield-moves, https:\/\/actorcore.reallusion.com\/3d-motion\/pack\/studio-mocap-hero-motion, https:\/\/actorcore.reallusion.com\/3d-motion\/pack\/studio-mocap-girl-dance, https:\/\/actorcore.reallusion.com\/3d-motion\/pack\/studio-mocap-evolution-of-dance-vol-1, https:\/\/actorcore.reallusion.com\/3d-motion\/pack\/studio-mocap-evolution-of-dance-vol-2, https:\/\/actorcore.reallusion.com\/3d-motion\/pack\/iclone-motion-pack\u2014street-dance-locking."},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"crossref","unstructured":"Diederik\u00a0M. Roijers Peter Vamplew Shimon Whiteson and Richard Dazeley. 2013. A Survey of Multi-Objective Sequential Decision-Making. J. Artificial Intelligence Research 48 1 (Oct. 2013) 67\u2013113.","DOI":"10.1613\/jair.3987"},{"key":"e_1_3_3_3_57_1","series-title":"Proceedings of Machine Learning Research","first-page":"1889","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","volume":"37","author":"Schulman John","year":"2015","unstructured":"John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz. 2015a. Trust Region Policy Optimization. In Proceedings of the 32nd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a037), Francis Bach and David Blei (Eds.). PMLR, Lille, France, 1889\u20131897. https:\/\/proceedings.mlr.press\/v37\/schulman15.html"},{"key":"e_1_3_3_3_58_1","unstructured":"John Schulman Philipp Moritz Sergey Levine Michael Jordan and Pieter Abbeel. 2015b. High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1506.02438 (2015)."},{"key":"e_1_3_3_3_59_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR abs\/1707.06347 (2017). arXiv:https:\/\/arXiv.org\/abs\/1707.06347http:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"crossref","unstructured":"Adriana Schulz Harrison Wang Eitan Grinspun Justin Solomon and Wojciech Matusik. 2018. Interactive exploration of design trade-offs. ACM Trans. Graph. 37 4 Article 131 (July 2018) 14\u00a0pages. doi:10.1145\/3197517.3201385","DOI":"10.1145\/3197517.3201385"},{"key":"e_1_3_3_3_61_1","series-title":"(SCA \u201924)","first-page":"1","volume-title":"Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation","author":"Serifi Agon","year":"2024","unstructured":"Agon Serifi, Ruben Grandia, Espen Knoop, Markus Gross, and Moritz B\u00e4cher. 2024. VMP: Versatile Motion Priors for Robustly Tracking Motion on Physical Characters. In Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation (Montreal, Quebec, Canada) (SCA \u201924). Eurographics Association, Goslar, DEU, 1\u201311. doi:10.1111\/cgf.15175"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570470"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276511"},{"key":"e_1_3_3_3_64_1","volume-title":"Reinforcement learning: An introduction (second ed.)","author":"Sutton Richard\u00a0S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement learning: An introduction (second ed.). The MIT Press, Cambridge, MA, USA."},{"key":"e_1_3_3_3_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610449"},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"crossref","unstructured":"Chen Tessler Yunrong Guo Ofir Nabati Gal Chechik and Xue\u00a0Bin Peng. 2024. MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting. ACM Trans. Graph. 43 6 Article 209 (Nov. 2024) 21\u00a0pages. doi:10.1145\/3687951","DOI":"10.1145\/3687951"},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591541"},{"key":"e_1_3_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304652.3304697"},{"key":"e_1_3_3_3_69_1","unstructured":"Faraz Torabi Garrett Warnell and Peter Stone. 2018b. Generative adversarial imitation from observation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1807.06158 (2018)."},{"key":"e_1_3_3_3_70_1","unstructured":"Kristof Van\u00a0Moffaert and Ann Now\u00e9. 2014. Multi-Objective Reinforcement Learning Using Sets of Pareto Dominating Policies. Journal of Machine Learning Research 15 1 (2014) 3483\u20133512."},{"key":"e_1_3_3_3_71_1","unstructured":"Tingwu Wang Yunrong Guo Maria Shugrina and Sanja Fidler. 2020. UniCon: Universal Neural Controller For Physics-based Character Motion. arxiv:https:\/\/arXiv.org\/abs\/2011.15119\u00a0[cs.GR]"},{"key":"e_1_3_3_3_72_1","doi-asserted-by":"publisher","unstructured":"Jungdam Won Deepak Gopinath and Jessica Hodgins. 2020. A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters. ACM Trans. Graph. 39 4 Article 33 (2020). 10.1145\/3386569.3392381","DOI":"10.1145\/3386569.3392381"},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"crossref","unstructured":"Jungdam Won Deepak Gopinath and Jessica Hodgins. 2022. Physics-based character controllers using conditional VAEs. ACM Trans. Graph. 41 4 Article 96 (July 2022) 12\u00a0pages. doi:10.1145\/3528223.3530067","DOI":"10.1145\/3528223.3530067"},{"key":"e_1_3_3_3_74_1","doi-asserted-by":"crossref","unstructured":"Jungdam Won Jongho Park Kwanyu Kim and Jehee Lee. 2017. How to train your dragon: example-guided control of flapping flight. ACM Trans. Graph. 36 6 Article 198 (Nov. 2017) 13\u00a0pages. doi:10.1145\/3130800.3130833","DOI":"10.1145\/3130800.3130833"},{"key":"e_1_3_3_3_75_1","unstructured":"Philipp Wu Alejandro Escontrela Danijar Hafner Ken Goldberg and Pieter Abbeel. 2022. DayDreamer: World Models for Physical Robot Learning. arxiv:https:\/\/arXiv.org\/abs\/2206.14176\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/2206.14176"},{"key":"e_1_3_3_3_76_1","unstructured":"Sitao Xiang and Hao Li. 2020. Revisiting the continuity of rotation representations in neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.06234 (2020)."},{"key":"e_1_3_3_3_77_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525921"},{"key":"e_1_3_3_3_78_1","doi-asserted-by":"crossref","unstructured":"Pei Xu and Ioannis Karamouzas. 2021. A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control. Proc. ACM Comput. Graph. Interact. Tech. 4 3 Article 44 (Sept. 2021) 22\u00a0pages. doi:10.1145\/3480148","DOI":"10.1145\/3480148"},{"key":"e_1_3_3_3_79_1","doi-asserted-by":"crossref","unstructured":"Pei Xu Xiumin Shang Victor Zordan and Ioannis Karamouzas. 2023. Composite Motion Learning with Task Control. ACM Trans. Graph. 42 4 Article 93 (July 2023) 16\u00a0pages. doi:10.1145\/3592447","DOI":"10.1145\/3592447"},{"key":"e_1_3_3_3_80_1","volume-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","author":"Yang Runzhe","year":"2019","unstructured":"Runzhe Yang, Xingyuan Sun, and Karthik Narasimhan. 2019. A generalized algorithm for multi-objective reinforcement learning and policy adaptation. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_3_3_81_1","doi-asserted-by":"crossref","unstructured":"Heyuan Yao Zhenhua Song Baoquan Chen and Libin Liu. 2022. ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters. ACM Trans. Graph. 41 6 Article 183 (Nov. 2022) 16\u00a0pages. doi:10.1145\/3550454.3555434","DOI":"10.1145\/3550454.3555434"},{"key":"e_1_3_3_3_82_1","doi-asserted-by":"crossref","unstructured":"Wenhao Yu Greg Turk and C.\u00a0Karen Liu. 2018. Learning symmetric and low-energy locomotion. ACM Trans. Graph. 37 4 Article 144 (July 2018) 12\u00a0pages. doi:10.1145\/3197517.3201397","DOI":"10.1145\/3197517.3201397"},{"key":"e_1_3_3_3_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"e_1_3_3_3_84_1","doi-asserted-by":"crossref","unstructured":"Qingxu Zhu He Zhang Mengting Lan and Lei Han. 2023. Neural Categorical Priors for Physics-Based Character Control. ACM Trans. Graph. 42 6 Article 178 (Dec. 2023) 16\u00a0pages. doi:10.1145\/3618397","DOI":"10.1145\/3618397"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:51:30Z","timestamp":1774018290000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730656"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":83,"alternative-id":["10.1145\/3721238.3730656","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730656","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}